activity
20152022
most citedAutoregressive Image Generation using Residual Quantization

10 citations · 31 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG20218 cited

Automated Learning Rate Scheduler for Large-batch Training

Chiheon Kim, Saehoon Kim, Jongmin Kim +2

Large-batch training has been essential in leveraging large-scale datasets and models in deep learning. While it is computationally beneficial to use large batch sizes, it often re…

cs.LG20215 cited

Hybrid Generative-Contrastive Representation Learning

Saehoon Kim, Sungwoong Kim, Juho Lee

Unsupervised representation learning has recently received lots of interest due to its powerful generalizability through effectively leveraging large-scale unlabeled data. There ar…

cs.LG20195 cited

MxML: Mixture of Meta-Learners for Few-Shot Classification

Minseop Park, Jungtaek Kim, Saehoon Kim +2

A meta-model is trained on a distribution of similar tasks such that it learns an algorithm that can quickly adapt to a novel task with only a handful of labeled examples. Most of…

cs.LG2019

Scalable and Order-robust Continual Learning with Additive Parameter Decomposition

Jaehong Yoon, Saehoon Kim, Eunho Yang +1

While recent continual learning methods largely alleviate the catastrophic problem on toy-sized datasets, some issues remain to be tackled to apply them to real-world problem domai…

cs.LG2018

Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning

Yanbin Liu, Juho Lee, Minseop Park +4

The goal of few-shot learning is to learn a classifier that generalizes well even when trained with a limited number of training instances per class. The recently introduced meta-l…